AI Chat AI Image Generator AI Video Text to Speech

Weakly Supervised Multi-Embeddings Learning of Acoustic Models

12/20/2014

∙

by Gabriel Synnaeve, et al.

∙

∙

We trained a Siamese network with multi-task same/different information on a speech dataset, and found that it was possible to share a network for both tasks without a loss in performance. The first task was to discriminate between two same or different words, and the second was to discriminate between two same or different talkers.

Gabriel Synnaeve
73 publications
Emmanuel Dupoux
61 publications

research

∙ 04/23/2017

Learning weakly supervised multimodal phoneme embeddings

Recent works have explored deep architectures for learning multimodal sp...

0 Rahma Chaabouni, et al. ∙

research

∙ 10/01/2019

Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings

Acoustic word embeddings — fixed-dimensional vector representations of a...

0 Myunghun Jung, et al. ∙

research

∙ 11/05/2018

Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation

End-to-end Speech Translation (ST) models have many potential advantages...

0 Ye Jia, et al. ∙

research

∙ 06/07/2021

Weakly-supervised word-level pronunciation error detection in non-native English speech

We propose a weakly-supervised model for word-level mispronunciation det...

0 Daniel Korzekwa, et al. ∙

research

∙ 08/06/2023

Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables

Sensor data streams from wearable devices and smart environments are wid...

0 Taoran Sheng, et al. ∙

research

∙ 04/23/2021

Weakly-supervised Multi-task Learning for Multimodal Affect Recognition

Multimodal affect recognition constitutes an important aspect for enhanc...

13 Wenliang Dai, et al. ∙

research

∙ 01/11/2019

Advanced Rich Transcription System for Estonian Speech

This paper describes the current TTÜ speech transcription system for Est...

0 Tanel Alumäe, et al. ∙